Boxhead: A Dataset for Learning Hierarchical Representations
Disentanglement is hypothesized to be beneficial towards a number of downstream tasks. However, a common assumption in learning disentangled representations is that the data generative factors are statistically independent. As current methods are almost solely evaluated on toy datasets where this ideal assumption holds, we investigate their performance in hierarchical settings, a relevant feature of real-world data. In this work, we introduce Boxhead, a dataset with hierarchically structured ground-truth generative factors. We use this novel dataset to evaluate the performance of state-of-the-art autoencoder-based disentanglement models and observe that hierarchical models generally outperform single-layer VAEs in terms of disentanglement of hierarchically arranged factors.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementSimilar Papers 제목 키워드 기반
Are "Hierarchical" Visual Representations Hierarchical?
Learned visual representations often capture large amounts of semantic information for accurate downstream applications. Human understanding of the world is fundamentally grounded in hierarchy. To mimic this and further …
Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection
In this paper, we study context-response matching with pre-trained contextualized representations for multi-turn response selection in retrieval-based chatbots. Existing models, such as Cove and ELMo, are trained with li…
DecoderDialogue GenerationRetrievalSentenceOn the Transferability of Representations in Neural Networks Between Datasets and Tasks
Deep networks, composed of multiple layers of hierarchical distributed representations, tend to learn low-level features in initial layers and transition to high-level features towards final layers. Paradigms such as tra…
Continual LearningMulti-Task LearningTransfer LearningLearning Hyperbolic Representations for Unsupervised 3D Segmentation
There exists a need for unsupervised 3D segmentation on complex volumetric data, particularly when annotation ability is limited or discovery of new categories is desired. Using the observation that much of 3D volumetric…
SegmentationTripletA Subpath Kernel for Learning Hierarchical Image Representations
Tree kernels have demonstrated their ability to deal with hierarchical data, as the intrinsic tree structure often plays a discriminative role. While such kernels have been successfully applied to various domains such as…